INDEX

Explanations

patterns and structures indicative of programming syntax or code expressions

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 0-gemmascope-res-65k

Configuration

google/gemma-scope-2b-pt-res/layer_0/width_65k/average_l0_73

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

65,536

Data Type

float32

Hook Name

blocks.0.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Monfieur

-1.09

Efq

-1.05

 ―――――

-0.96

CodeAttribute

-0.94

 myſelf

-0.91

 Anſ

-0.90

 Majefty

-0.90

 Cæsar

-0.89

 itſelf

-0.88

 Normdatei

-0.88

POSITIVE LOGITS

</tr>

0.92

<eos>

0.69

↵

0.68

0.67

0.63

...

0.62

 Everyone

0.62

0.60

Activations Density 0.107%

patterns and structures indicative of programming syntax or code expressions

No Comments

No Known Activations